Intelligent settings of onboard sensors on a vehicle

Abstract

An embodiment includes detecting a future terrain metric by a vehicle. The embodiment includes responsive to detecting the future terrain metric, computing a sensor adjustment metric based on a current terrain metric and the future terrain metric. The embodiment also includes adjusting an onboard sensor of the vehicle based on the sensor adjustment metric.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 detecting a future terrain metric by a vehicle;   responsive to detecting the future terrain metric, computing a sensor adjustment metric based on a current terrain metric and the future terrain metric; and   adjusting an onboard sensor of the vehicle based on the sensor adjustment metric wherein the sensor adjustment metric is optimized comprising training a machine learning model based on vehicle information, sensor data, sensor location, road condition data, weather data and user feedback to output an optimized sensor adjustment metric, the training further comprising weighing at least one of the vehicle information, the sensor data, the sensor location, the road condition data, and the weather data against user feedback.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the future terrain metric comprises a feature of a terrain on which the vehicle is moving. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the onboard sensor is selected from a group consisting of a vision-based sensor, a radar-based sensor, an audio-based sensor, a satellite-based sensor, a cloud-based sensor and a light-based sensor. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the onboard sensor is adjusted angularly, radially, vertically and horizontally. 
     
     
         5 . The computer-implemented method of  claim 1  wherein the sensor adjustment metric comprises a sensor height, a sensor angle, and a sensor rotation. 
     
     
         6 . The computer-implemented method of  claim 1 , the training further comprising weighing the user feedback less than weighing one of the vehicle information, the sensor data, the sensor location, the road condition data, and the weather data. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the computing the sensor adjustment metric comprises training the machine learning model based on the current terrain metric and the future terrain metric. 
     
     
         8 . A non-transitory computer readable medium comprising a computer program comprising machine readable instructions that, when executed by a processor, performs:
 detecting a future terrain metric by a vehicle;   responsive to detecting the future terrain metric, computing a sensor adjustment metric based on a current terrain metric and the future terrain metric; and   adjusting an onboard sensor of the vehicle based on the sensor adjustment metric wherein the sensor adjustment metric is optimized comprising training a machine learning model based on vehicle information, sensor data, sensor location, road condition data, weather data and user feedback to output an optimized sensor adjustment metric, the training further comprising weighing at least one of the vehicle information, the sensor data, the sensor location, the road condition data, and the weather data against user feedback.   
     
     
         9 . The non-transitory computer readable medium of  claim 8 , wherein the future terrain metric comprises a feature of a terrain on which the vehicle is moving. 
     
     
         10 . The non-transitory computer readable medium of  claim 8 , wherein the onboard sensor is selected from a group consisting of a vision-based sensor, a radar-based sensor, an audio-based sensor, a satellite-based sensor, a cloud-based sensor and a light-based sensor. 
     
     
         11 . The non-transitory computer readable medium of  claim 8 , wherein the onboard sensor is adjusted angularly, radially, vertically and horizontally. 
     
     
         12 . The non-transitory computer readable medium of  claim 8 , wherein the sensor adjustment metric comprises a sensor height, a sensor angle, and a sensor rotation. 
     
     
         13 . The non-transitory computer readable medium of  claim 8 , the training further comprising weighing the user feedback less than weighing one of the vehicle information, the sensor data, the sensor location, the road condition data, and the weather data. 
     
     
         14 . The non-transitory computer readable medium of  claim 8 , wherein the computing the sensor adjustment metric comprises training the machine learning model based on the current terrain metric and the future terrain metric. 
     
     
         15 . A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:
 detecting a future terrain metric by a vehicle;   responsive to detecting the future terrain metric, computing a sensor adjustment metric based on a current terrain metric and the future terrain metric; and   adjusting an onboard sensor of the vehicle based on the sensor adjustment metric wherein the sensor adjustment metric is optimized comprising training a machine learning model based on vehicle information, sensor data, sensor location, road condition data, weather data and user feedback to output an optimized sensor adjustment metric, the training further comprising weighing at least one of the vehicle information, the sensor data, the sensor location, the road condition data, and the weather data against user feedback.   
     
     
         16 . The computer system of  claim 15 , wherein the onboard sensor is selected from a group consisting of a vision-based sensor, a radar-based sensor, an audio-based sensor, a satellite-based sensor, a cloud-based sensor and a light-based sensor. 
     
     
         17 . The computer system of  claim 15 , wherein the onboard sensor is adjusted angularly, radially, vertically and horizontally. 
     
     
         18 . The computer system of  claim 15 , wherein the sensor adjustment metric comprises a sensor height, a sensor angle, and a sensor rotation. 
     
     
         19 . The computer system of  claim 15 , the training further comprising weighing the user feedback less than weighing one of the vehicle information, the sensor data, the sensor location, the road condition data, and the weather data. 
     
     
         20 . The computer system of  claim 15 , wherein the computing the sensor adjustment metric comprises training the machine learning model based on the current terrain metric and the future terrain metric.